drm/i915/gtt/dg1: add PTE_LM plumbing for ppGTT

For the PTEs we get an LM bit, to signal whether the page resides in
SMEM or LMEM.

BSpec: 45040

v2: just use gen8_pte_encode for dg1

Signed-off-by: Matthew Auld <[email protected]>
Cc: Joonas Lahtinen <[email protected]>
Signed-off-by: Daniele Ceraolo Spurio <[email protected]>
Signed-off-by: Niranjana Vishwanathapura <[email protected]>
Signed-off-by: Venkata Sandeep Dhanalakota <[email protected]>
Reviewed-by: Chris Wilson <[email protected]>
Signed-off-by: Chris Wilson <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Signed-off-by: Daniel Vetter <[email protected]>

Author: matt-auld

drivers/gpu/drm/i915/gt/gen8_ppgtt.c

@@ -5,6 +5,8 @@
 
 #include <linux/log2.h>
 
+#include "gem/i915_gem_lmem.h"
+
 #include "gen8_ppgtt.h"
 #include "i915_scatterlist.h"
 #include "i915_trace.h"
@@ -35,6 +37,9 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	if (unlikely(flags & PTE_READ_ONLY))
 		pte &= ~_PAGE_RW;
 
+	if (flags & PTE_LM)
+		pte |= GEN12_PPGTT_PTE_LM;
+
 	switch (level) {
 	case I915_CACHE_NONE:
 		pte |= PPAT_UNCACHED;
@@ -558,6 +563,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 
 static int gen8_init_scratch(struct i915_address_space *vm)
 {
+	u32 pte_flags;
 	int ret;
 	int i;
 
@@ -581,9 +587,13 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 	if (ret)
 		return ret;
 
+	pte_flags = vm->has_read_only;
+	if (i915_gem_object_is_lmem(vm->scratch[0]))
+		pte_flags |= PTE_LM;
+
 	vm->scratch[0]->encode =
 		gen8_pte_encode(px_dma(vm->scratch[0]),
-				I915_CACHE_LLC, vm->has_read_only);
+				I915_CACHE_LLC, pte_flags);
 
 	for (i = 1; i <= vm->top; i++) {
 		struct drm_i915_gem_object *obj;

drivers/gpu/drm/i915/gt/intel_gtt.h

@@ -85,6 +85,8 @@ typedef u64 gen8_pte_t;
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
 #define BYT_PTE_WRITEABLE		REG_BIT(1)
 
+#define GEN12_PPGTT_PTE_LM BIT_ULL(11)
+
 /*
  * Cacheability Control is a 4-bit value. The low three bits are stored in bits
  * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE.
@@ -264,6 +266,7 @@ struct i915_address_space {
 			  enum i915_cache_level level,
 			  u32 flags); /* Create a valid PTE */
 #define PTE_READ_ONLY	BIT(0)
+#define PTE_LM		BIT(1)
 
 	void (*allocate_va_range)(struct i915_address_space *vm,
 				  struct i915_vm_pt_stash *stash,

drivers/gpu/drm/i915/gt/intel_ppgtt.c

@@ -5,6 +5,8 @@
 
 #include <linux/slab.h>
 
+#include "gem/i915_gem_lmem.h"
+
 #include "i915_trace.h"
 #include "intel_gtt.h"
 #include "gen6_ppgtt.h"
@@ -192,6 +194,8 @@ void ppgtt_bind_vma(struct i915_address_space *vm,
 	pte_flags = 0;
 	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
+	if (i915_gem_object_is_lmem(vma->obj))
+		pte_flags |= PTE_LM;
 
 	vm->insert_entries(vm, vma, cache_level, pte_flags);
 	wmb();